Paper ID: 2412.01541

Effectiveness of L2 Regularization in Privacy-Preserving Machine Learning

Nikolaos Chandrinos (1), Iliana Loi (2), Panagiotis Zachos (2), Ioannis Symeonidis (1), Aristotelis Spiliotis (1), Maria Panou (1), Konstantinos Moustakas (2) ((1) Human Factors and Vehicle Technology, Hellenic Institute of Transport, Centre for Research and Technology Hellas, Thermi, Greece, (2) Wire Communications and Information Technology Laboratory, Dept. of Electrical and Computer Engineering, University of Patras, Patras, Greece)

Artificial intelligence, machine learning, and deep learning as a service have become the status quo for many industries, leading to the widespread deployment of models that handle sensitive data. Well-performing models, the industry seeks, usually rely on a large volume of training data. However, the use of such data raises serious privacy concerns due to the potential risks of leaks of highly sensitive information. One prominent threat is the Membership Inference Attack, where adversaries attempt to deduce whether a specific data point was used in a model's training process. An adversary's ability to determine an individual's presence represents a significant privacy threat, especially when related to a group of users sharing sensitive information. Hence, well-designed privacy-preserving machine learning solutions are critically needed in the industry. In this work, we compare the effectiveness of L2 regularization and differential privacy in mitigating Membership Inference Attack risks. Even though regularization techniques like L2 regularization are commonly employed to reduce overfitting, a condition that enhances the effectiveness of Membership Inference Attacks, their impact on mitigating these attacks has not been systematically explored.

Submitted: Dec 2, 2024